Skill Invocation Chaining for Speech Assistant Input Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech processing systems require users to provide multiple specific inputs to activate or initiate multiple skills for different tasks, leading to increased user input requirements and complexity.
Innovation Solution
The system allows a skill to invoke another skill to perform an action, even if the action was not requested by the user, enabling the execution of multiple actions with fewer user inputs. This is achieved through skill registration, where skills can register to perform particular actions that may be executed by other skills, allowing one skill to be indicated as a provider or consumer of actions from other skills.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If multiple specific inputs are required to activate multiple skills, then each skill can be precisely controlled, but user input requirements and interaction complexity increase
Solution Approach 1:
The patent combines multiple skill invocations into a single user input by allowing skills to invoke other skills automatically. When a user activates one skill, the system can chain additional skills to perform related actions without requiring separate user commands for each action, thus merging multiple operations into one interaction.
Solution Approach 2:
The system performs preliminary actions by pre-configuring skill chains where skills are prepared to automatically invoke other skills based on predefined relationships. This preliminary arrangement of skill invocations eliminates the need for users to explicitly request each subsequent action, reducing input requirements while maintaining functional precision.
2Productivity
If skills can invoke other skills automatically, then multiple tasks can be completed with fewer inputs, but the system architecture becomes more complex
Solution Approach 1:
The skill registration system provides universal functionality by allowing any skill to register as a provider or consumer of actions from other skills. This multi-functional registration mechanism enables flexible skill chaining where skills can invoke other skills based on their registered relationships, improving task completion efficiency without requiring separate specialized systems for each skill type.
Solution Approach 2:
The skill registration system acts as an intermediary layer between skills, managing the complexity of skill-to-skill invocations. By centralizing the registration and coordination of skill relationships, the intermediary system handles the architectural complexity while enabling skills to automatically invoke each other for improved productivity.
3Reliability
If skills register to perform particular actions, then action coordination between skills is improved, but system configuration complexity increases
Solution Approach 1:
The skill registration system enables skills to self-configure their relationships by allowing each skill to register itself as a provider or consumer of actions. This self-service approach improves action coordination reliability through explicit skill declarations while reducing the need for centralized manual configuration, thereby managing system complexity through automated skill self-configuration.
Data Source
AI summary
Described herein is a system for enabling a user to perform complex goals using multiple skills/applications of an intelligent assistant device. Skills may register as consumers of an action or providers of an action, and the consumer skills may be configured to invoke provider skills to perform actions. The system receives a request to perform an action from a skill along with some action data. The system validates the action data, selects another skill to perform the action, and forwards the request to the selected skill to perform the action.